397 search results - page 47 / 80 » Lattice-based System Combination for Statistical Machine Tra... |
EMNLP
2008
13 years 9 months ago
2008
Minimum-error-rate training (MERT) is a bottleneck for current development in statistical machine translation because it is limited in the number of weights it can reliably optimi...
COLING
2010
13 years 2 months ago
2010
Hindi and Urdu share a common phonology, morphology and grammar but are written in different scripts. In addition, the vocabularies have also diverged significantly especially in ...
IR
2008
13 years 7 months ago
2008
CLIR resources, such as dictionaries and parallel corpora, are scarce for special domains. Obtaining comparable corpora automatically for such domains could be an answer to this p...
ACL
2008
13 years 9 months ago
2008
Automatic word alignment is a key step in training statistical machine translation systems. Despite much recent work on word alignment methods, alignment accuracy increases often ...
ACL
2009
13 years 5 months ago
2009
We investigate the use of Fisher's exact significance test for pruning the translation table of a hierarchical phrase-based statistical machine translation system. In additio...